Bridging artificial intelligence and fucoxanthin for the recovery and quantification from microalgae

Fucoxanthin is a carotenoid that possesses various beneficial medicinal properties for human well-being. However, the current extraction technologies and quantification techniques are still lacking in terms of cost validation, high energy consumption, long extraction time, and low yield production. To date, artificial intelligence (AI) models can assist and improvise the bottleneck of fucoxanthin extraction and quantification process by establishing new technologies and processes which involve big data, digitalization, and automation for efficiency fucoxanthin production. This review highlights the application of AI models such as artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS), capable of learning patterns and relationships from large datasets, capturing non-linearity, and predicting optimal conditions that significantly impact the fucoxanthin extraction yield. On top of that, combining metaheuristic algorithm such as genetic algorithm (GA) can further improve the parameter space and discovery of optimal conditions of ANN and ANFIS models, which results in high R2 accuracy ranging from 98.28% to 99.60% after optimization. Besides, AI models such as support vector machine (SVM), convolutional neural networks (CNNs), and ANN have been leveraged for the quantification of fucoxanthin, either computer vision based on color space of images or regression analysis based on statistical data. The findings are reliable when modeling for the concentration of pigments with high R2 accuracy ranging from 66.0% - 99.2%. This review paper has reviewed the feasibility and potential of AI for the extraction and quantification purposes, which can reduce the cost, accelerate the fucoxanthin yields, and development of fucoxanthin-based products.

Maximizing the extraction yield of plant gum exudate using response surface methodology and artificial neural networking and pharmacological characterization

Prunus armeniaca gum is used as food additive and ethno medicinal purpose. Two empirical models response surface methodology and artificial neural network were used to search for optimized extraction parameters for gum extraction. A four-factor design was implemented for optimization of extraction process for maximum yield which was obtained under the optimized extraction parameter (temperature, pH, extraction time, and gum/water ratio). Micro and macro-elemental composition of gum was determined by using laser induced breakdown spectroscopy. Gum was evaluated for toxicological effect and pharmacological properties. The maximum predicted yield obtained by response surface methodology and artificial neural network was 30.44 and 30.70% which was very close to maximum experimental yield 30.23%. Laser induced breakdown spectroscopic spectra confirmed the presence Calcium, Potassium, Magnesium, Sodium, Lithium, Carbon, Hydrogen, Nitrogen and Oxygen. Acute oral toxicity study showed that gum is non-toxic up to 2000 mg/Kg body weight in rabbits, accompanied by high cytotoxic effects of gum against HepG2 and MCF-7cells by MTT assay. Overall, Aqueous solution of gum showed various pharmacological activities with significant value of antioxidant, antibacterial, anti-nociceptive, anti-cancer, anti-inflammatory and thrombolytic activities. Thus, optimization of parameters using mathematical models cans offer better prediction and estimations with enhanced pharmacological properties of extracted components.

Modeling and Optimization of Ultrasound-Assisted Extraction of Bioactive Compounds from Allium sativum Leaves Using Response Surface Methodology and Artificial Neural Network Coupled with Genetic Algorithm

This study explains the effect of ultrasound on the extraction of the bioactive compounds from garlic (Allium sativum L.) leaf powder. The experiment was carried out by varying the ultrasound amplitude (30-60%), treatment time (5-15 min), and ethanol concentration (40-60%) required to obtain the maximum extraction yield of total phenol content (TPC), total flavonoid content (TFC), and antioxidant activity. Rotatable central composite design (RCCD) provided experimental parameter combinations in the ultrasound-assisted extraction (UAE) of garlic leaf powder. The values of extraction yield, TPC, TFC, and antioxidant activity for the optimized condition of RSM were obtained at 53% amplitude, 13 min of treatment time, and 50% ethanol concentration. The values of the target compounds predicted at this optimized condition from RSM were 32.2% extraction yield, 9.9 mg GAE/g TPC, 6.8 mg QE/g TFC, and 58% antioxidant activity. The ANN-GA optimized condition for the leaf extracts was obtained at 60% amplitude, 13 min treatment time, and 53% ethanol concentration. The predicted values of optimized condition obtained by ANN-GA were recorded as 32.1738% extraction yield and 9.8661 mg GAE/g, 6.8398 mg QE/g, and 58.5527% for TPC, TFC, and antioxidant activity, respectively. The matured leaves of garlic, if not harvested during its cultivation, often go waste despite being rich in antioxidants and phenolic compounds. With the increased demand for the production of value-added products, the extraction of the bioactive compounds from garlic leaves can resolve waste management and potential health issues without affecting the crop yield through the process for high-end use in value addition.

Metabolite Profiling of Microwave-Assisted Sargassum fusiforme Extracts with Improved Antioxidant Activity Using Hybrid Response Surface Methodology and Artificial Neural Networking-Genetic Algorithm

Sargassum fusiforme (SF) is a popular edible brown macroalga found in Korea, Japan, and China and is known for its health-promoting properties. In this study, we used two sophisticated models to obtain optimized conditions for high antioxidant activity and metabolite profiling using high-resolution mass spectrometry. A four-factor central composite design was used to optimize the microwave-assisted extraction and achieve the maximum antioxidant activities of DPPH (Y1: 28.01 % inhibition), ABTS (Y2: 36.07 % inhibition), TPC (Y3: 43.65 mg GAE/g), and TFC (Y4: 17.67 mg CAE/g), which were achieved under the optimized extraction conditions of X1: 47.67 %, X2: 2.96 min, X3: 139.54 °C, and X4: 600.00 W. Moreover, over 79 secondary metabolites were tentatively identified, of which 12 compounds were reported for the first time in SF, including five phenolic (isopropyl 3-(3,4-dihydroxyphenyl)-2-hydroxypropanoate, 3,4-dihydroxyphenylglycol, scopoletin, caffeic acid 4-sulfate, and cinnamoyl glucose), two flavonoids (4',7-dihydroxyisoflavone and naringenin), three phlorotannins (diphlorethohydroxycarmalol, dibenzodioxin-1,3,6,8-tetraol, and fucophlorethol), and two other compounds (dihydroxyphenylalanine and 5-hydroxybenzofuran-2(3H)-one) being identified for the first time in optimized SF extract. These compounds may also be involved in improving the antioxidant potential of the extract. Therefore, optimized models can provide better estimates and predictive capabilities that would assist in finding new bioactive compounds with improved biological activities that can be further applied at a commercial level.

Optimization of accelerated solvent extraction of ellagitannins in black raspberry seeds using artificial neural network coupled with genetic algorithm

This study aimed to identify ellagitannins in black raspberry seeds (BRS) and to optimize accelerated solvent extraction of ellagitannins using an artificial neural network (ANN) coupled with genetic algorithm. Fifteen monomeric and dimeric ellagitannins were identified in BRS. For ANN modeling, extraction time, extraction temperature, and solvent concentration were set as input variables, and total ellagitannin content was set as output variable. The trained ANN had a mean squared error value of 0.0102 and a regression correlation coefficient of 0.9988. The predicted optimal extraction conditions for maximum total ellagitannin content were 63.7% acetone, 4.21 min, and 43.9 °C. The actual total ellagitannin content under the optimal extraction conditions was 13.4 ± 0.0 mg/g dry weight, and the prediction error was 0.75 ± 0.27%. This study is the first attempt to analyze the composition of ellagitannins in BRS and to determine optimal extraction conditions for maximum total ellagitannin content from BRS.

Application of Ultrasound as Clean Technology for Extraction of Specialized Metabolites From Stinging Nettle (Urtica dioica L.)

Nettle is a highly valued medicinal plant that is still largely neglected, both in terms of nutrition and use for pharmacological purposes. Tinctures, i.e., alcoholic extracts, are becoming increasingly popular nettle products, mainly because they allow better availability of phytochemicals and their stability over a longer period of time. The production of alcoholic extracts is a chemically demanding process that is still usually carried out using conventional techniques, which have numerous drawbacks. The use of green technologies such as ultrasound-assisted extraction (UAE), which is characterized by high efficiency of phytochemical extraction, shorter treatment time, and a much lower environmental footprint, is a suitable and sustainable solution. Therefore, the aim of this study is to determine the influence of the extraction method, conventional and ultrasound (by varying two ultrasound equipment systems), time and ethanol concentration on the extraction of specialized metabolites from nettle powder. Ultrasonic extraction using a probe system significantly contributed to increase the ascorbic acid yield, polyphenolic compounds, and antioxidant capacity of nettle extracts compared to conventional extraction. In addition, when a probe system was used during UAE, significantly less time was required for isolation of individual specialized metabolites compared to ultrasonic extraction in the bath. Ethanol concentration (50 and 80% v/v) also proved to be an important factor in the efficiency of extraction of specialized metabolites, with 80% ethanol being more effective for the isolation of ascorbic acid and pigment compounds (chlorophyll and carotenoids), while 50% v/v for the extraction of polyphenolic compounds. It can be concluded that extraction with the ultrasonic probe system is much more efficient in obtaining higher yields of specialized metabolites from nettle powder in a shorter time (average process duration 5-10 min) both compared to UAE in the bath and classical extraction. However, optimization of the key factors of time, solvent type, and ultrasonic power is necessary to maintain the nutritional quality of the nettle extract in order to obtain a final product with a high specialized metabolites content, antioxidant capacity, and functional value. The future application of alcoholic nettle extracts is based on the fact that these products have significant potential as functional foods and pharmacological preparations for the treatment of a number of but also to strengthen the immune system, mainly due to the rich nutritional composition and high content of various specialized metabolites. The prepared extracts can be safely taken orally by diluting the tinctures with water immediately before ingestion.